Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1049589 | Landscape and Urban Planning | 2012 | 9 Pages |
Urban areas are expanding at a very fast rate worldwide. The task of managing urban growth has increased in both scope and complexity and has become one of the most important challenges in the 21st century. This article aims to examine the urban development and optimize spatial patterns of future urban growth allocation based on scenarios to provide a basis for urban environmental management in the Kathmandu Valley, Nepal. We developed an artificial neural network based urban growth allocation model for the valley. This predictive model optimizes spatial patterns of future urban growth allocation under the three scenarios, i.e., spontaneous, environment-protecting, and resources-saving. The predicted spatial patterns mirrors where and how the urban development in the valley is likely heading by 2050 and provides a crucial information on land availability for future land development projects. The results suggest that the current urban development process is in critical stage where urban and peri-urban areas will face unprecedented stress on land resources costing river and forest ecosystems and other environmentally sensitive areas by the next decade. Rural vicinities will face regional imbalance on urban growth allocations. However, there are still possibilities to improve urban environment and manage the potential land demands in the valley by enforcing the urban growth policies strictly and altering the current growth trend as revealed in the environment-protecting and resources-saving scenarios.
► We calibrated ANN based urban growth model for the Kathmandu Valley. ► The model optimizes future urban growth allocation at multiple scenarios. ► The predicted spatial patterns mirror the time series urban development by 2050. ► We revealed crucial information on land availability for future land development. ► Sustainable urban development requires enforcing urban growth policies strictly.